Initial Stuff

Load in Initial Processing file (and dependencies)

source("InitialProcessing.R")
Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ──────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✓ ggplot2 3.3.5     ✓ purrr   0.3.4
✓ tibble  3.1.6     ✓ dplyr   1.0.7
✓ tidyr   1.1.4     ✓ stringr 1.4.0
✓ readr   2.0.0     ✓ forcats 0.5.1
── Conflicts ─────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()
New names:
* `` -> ...1
Rows: 73325 Columns: 97
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr  (1): ...1
dbl (96): 3-1-B-0-2_R1_filt.fastq.gz, 3-1-B-1-2_R1_filt.fastq.gz, 3-1-B-180_R1_filt.fastq.gz, 3-1-B-2...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
New names:
* `` -> ...1
Rows: 73325 Columns: 7
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr (7): ...1, Kingdom, Phylum, Class, Order, Family, Genus

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
Rows: 192 Columns: 16
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (13): Files, ID, Sample, Depth, Type, Paths, RenFiles, RenPaths, TrimmedFiles, TrimmedPaths, Filt...
dbl  (3): ReadDir, Station, Size

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
Rows: 91 Columns: 7
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (1): Depth
dbl (6): Station, Size_Class, Bin_Size, DNAperLiter, MassperLiter, ParticlesPerLiter

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
Rows: 96 Columns: 5
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (3): ID, Depth, Flag
dbl (2): Station, Size_Class

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
extract_numeric() is deprecated: please use readr::parse_number() instead
Joining, by = "TagLevel"
`summarise()` has grouped output by 'ID'. You can override using the `.groups` argument.
Warning: Removed 15 rows containing missing values (position_stack).
`summarise()` has grouped output by 'nASV'. You can override using the `.groups` argument.
Rows: 9 Columns: 7
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (1): Station
dbl (6): lat, long, UTMX, UTMY, depth, do

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
source("ChesapeakePersonalLibrary.R")

Cells/mg of particle

# my_sizes <- sort(unique(microbialAbundance$Size_Class))
# my_sizes
# scientific_10_c <- function(x) {
#     xout <- gsub("1e", "10^{", format(x),fixed=TRUE)
#     xout <- gsub("{-0", "{-", xout,fixed=TRUE)
#     xout <- gsub("{+", "{", xout,fixed=TRUE)
#     xout <- gsub("{0", "{", xout,fixed=TRUE)
#     xout <- paste(xout,"}",sep="")
#     return(parse(text=xout))
#     
# }
# 
# scale_y_log10nice <- function(name=NULL,omag=seq(-10,20),...) {
#     breaks10 <- 10^omag
#     scale_y_log10(breaks=breaks10,labels=scientific_10_c(breaks10),...)
# } # Reclocated to ChesapeakePersonalLibrary.R
abunPlot <- microbialAbundance %>% 
  filter(is.finite(MassperLiter)) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  mutate(copiesPerMg = copiesPerL / MassperLiter) %>%
  ggplot(aes(x = Size_Class, y = copiesPerMg, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice() +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "16s + 18s Genes / mg Particles", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
abunPlot

PPLPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  ggplot(aes(x = Size_Class, y = ParticlesPerLiter, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag=seq(-10,20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "Particles/L/mm", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
PPLPlot

ParticleMassPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  ggplot(aes(x = Size_Class, y = MassperLiter/ParticlesPerLiter, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "Dry Mass (mg) / Particle", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = .5))
ParticleMassPlot

Ibid but combined with data about particles and the CB map

I need to load over data from the CB-Bay project

source("CBMap.R")
Rows: 9 Columns: 7
── Column specification ─────────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (1): Station
dbl (6): lat, long, UTMX, UTMY, depth, do

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
library(cowplot)
library(grid)
library(gridExtra)

Attaching package: ‘gridExtra’

The following object is masked from ‘package:dplyr’:

    combine
x.grob <- textGrob(expression(paste("Particle Size (", mu, "m)")), 
                   gp=gpar(fontsize=16))
combinedPlot <- plot_grid(PPLPlot, ParticleMassPlot, abunPlot, nrow = 1, labels = c("B", "C", "D"))
meta2 <- grid.arrange(arrangeGrob(combinedPlot, bottom = x.grob))

cbMap

physical_particles <- plot_grid(cbMap, meta2, rel_widths = c(1,3), labels = c("A", ""))
physical_particles

ggsave("PhysicalParticles.png", physical_particles, height = 4, width = 8)

Examplar species plot

What are the most abundant ASVs from each cluster? Plot their abundance. Pick the prettiest few and plot

source("ClusteringCore.R")
hgroups_exemplars <- cutree(sclust, k = 10)
nonSpikes20C <- nonSpikes20 %>% left_join(
  tibble(ASV = names(hgroups_exemplars), cluster = hgroups_exemplars), by = "ASV")
ASVsToView <- nonSpikes20C %>%
  filter(Kingdom == "Bacteria") %>%
  group_by(ASV, cluster) %>%
  summarise(meanCopies = mean(copiesPerL)) %>%
  group_by(cluster) %>%
  summarize(topASV = ASV[which.max(meanCopies)])
`summarise()` has grouped output by 'ASV'. You can override using the `.groups` argument.
  
ASVsToView
nonSpikes20C %>% 
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster")) %>%
  group_by(ASV) %>%
  slice_head()
nonSpikes20C %>%
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster" = "cluster")) %>%
  filter(cluster <= 7, Depth %in% c("Surface", "Bottom"), !is.na(Depth)) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma")
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

Fig X. Copies per L

nonSpikes20C %>%
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster" = "cluster")) %>%
  filter(cluster <= 7, Depth %in% c("Surface", "Bottom"), !is.na(Depth)) %>%
  filter(!is.na(MassperLiter)) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/MassperLiter, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma")
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

Fig X + 1. Copies per mg stuff. I don’t love these examples because there is a bunch of station to station ariance, and you never see things that like, always show up at large stations.

I wonder if I can find some good examples of consistantly large particle stuff or something.

What if

I look for things that have high positive slope coefficients between size and normalized copies per L. And select for high mean abundance and high slope. And use site as a random effect? Would be nice to have some things that are intermediately high though. Some sort of polynomial regression?

nest20 <- nonSpikes20 %>%
  select(ASV, Station:ParticlesPerLiter, copiesPerL) %>%
  mutate(Station = as.factor(Station)) %>%
  group_by(ASV) %>%
  nest()
TestSub <- nest20[[2]][[1]] %>% ungroup()
TestSub
library(lme4)
Loading required package: Matrix

Attaching package: ‘Matrix’

The following objects are masked from ‘package:tidyr’:

    expand, pack, unpack
library(broom)
library(broom.mixed)
lm(log(copiesPerL/Bin_Size) ~ log(Size_Class), data = TestSub) %>% tidy()
lmer(log(copiesPerL/Bin_Size) ~ log(Size_Class) + (Size_Class|Station) + (Size_Class|Depth) , data = TestSub %>% 
       mutate(as.factor(Station))) %>% AIC()
boundary (singular) fit: see ?isSingular
[1] 294.8901
lmer(log(copiesPerL/Bin_Size) ~ log(Size_Class) + (1|Station) + (1|Depth) , data = TestSub %>% 
       mutate(as.factor(Station))) %>% AIC() # Better
[1] 284.1189
modDf <- nest20 %>%
  mutate(mod = map(data, 
                   ~lmer(log((copiesPerL+1)/Bin_Size) ~ log(Size_Class) +
                           (Size_Class|Station) + (Size_Class|Depth), data = .)
  )
  )
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 147: ASV = "ASV_1502".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 147: ASV = "ASV_1502".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 214: ASV = "ASV_186".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 214: ASV = "ASV_186".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 230: ASV = "ASV_197".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 1 negative eigenvalues
ℹ The warning occurred in group 230: ASV = "ASV_197".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 239: ASV = "ASV_2015".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 239: ASV = "ASV_2015".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 275: ASV = "ASV_2299".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 275: ASV = "ASV_2299".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 324: ASV = "ASV_280".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 324: ASV = "ASV_280".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 419: ASV = "ASV_407".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 419: ASV = "ASV_407".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge with max|grad| = 2.37793 (tol = 0.002, component 1)
ℹ The warning occurred in group 458: ASV = "ASV_468".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?;Model is nearly unidentifiable: large eigenvalue ratio
 - Rescale variables?
ℹ The warning occurred in group 458: ASV = "ASV_468".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 478: ASV = "ASV_5".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 478: ASV = "ASV_5".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 566: ASV = "ASV_657".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 1 negative eigenvalues
ℹ The warning occurred in group 566: ASV = "ASV_657".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 595: ASV = "ASV_71".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 1 negative eigenvalues
ℹ The warning occurred in group 595: ASV = "ASV_71".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge with max|grad| = 1.37981 (tol = 0.002, component 1)
ℹ The warning occurred in group 608: ASV = "ASV_730".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model is nearly unidentifiable: very large eigenvalue
 - Rescale variables?;Model is nearly unidentifiable: large eigenvalue ratio
 - Rescale variables?
ℹ The warning occurred in group 608: ASV = "ASV_730".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 635: ASV = "ASV_789".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 1 negative eigenvalues
ℹ The warning occurred in group 635: ASV = "ASV_789".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 648: ASV = "ASV_817".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 648: ASV = "ASV_817".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ unable to evaluate scaled gradient
ℹ The warning occurred in group 705: ASV = "ASV_94".
Warning: Problem with `mutate()` column `mod`.
ℹ `mod = map(...)`.
ℹ Model failed to converge: degenerate  Hessian with 2 negative eigenvalues
ℹ The warning occurred in group 705: ASV = "ASV_94".
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
boundary (singular) fit: see ?isSingular
modDf01 <- modDf %>% 
  mutate(tidied = map(mod, tidy)) %>%
  unnest(tidied) %>%
  select(-data, -mod)
modDf02 <- modDf01 %>%
  filter(term == "log(Size_Class)") %>%
  select(ASV, estimate, std.error)
modDf02 %>%
  ggplot(aes(x = estimate)) + geom_histogram() +
  scale_x_continuous(breaks = seq(from = -4, to = 2, by = 1))
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

There are some things that are ore abundant in the large particles

So Many ASVs. How do I ID the ones I want?

I kind of want to look at average concentrations (or sums)

SlopesAndMeans <- nonSpikes20 %>%
  #filter(Kingdom == "Bacteria") %>%
  group_by(ASV) %>%
  summarise(meanCopies = mean(copiesPerL)) %>%
  left_join(modDf02, by = "ASV")
SlopesAndMeans %>% head()
SlopesAndMeans %>%
  filter(estimate >= 0) %>%
  ggplot(aes(x = estimate, y = meanCopies, label = ASV)) +
  geom_point() +
  geom_label_repel()
Warning: ggrepel: 1 unlabeled data points (too many overlaps). Consider increasing max.overlaps

ASV 13 looks promising

taxa %>% 
  filter(ASV %in% c("ASV_13", "ASV_23", "ASV_58"))

The big stuff are all cyanos! Huh.

Targets <- SlopesAndMeans %>% filter(estimate > 0, meanCopies > 1e5) %>% pull(ASV)
taxa %>%
  filter(ASV %in% Targets)
Horses <- SlopesAndMeans %>% 
  left_join(taxa, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 0e5) %>%
  arrange(-meanCopies)
Horses

Ok. Big stuff are cyanos and Planctomycetes, and apparently Spiders. Also apparently some proteos of different stripes. Rhodobacter are cool though.

nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  filter(ASV == "ASV_7") %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies < 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

Lets look at these!

I like, as examples Paracoccus (a Rhodobacter) -ASV_459 Synechococcus_CC9902 – ASV_23 SAR11_Clade – ASV_3

nonSpikes20 %>%
  filter(ASV %in% c("ASV_3", "ASV_23", "ASV_459"), Depth != "Oxy") %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 3) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station")
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

Module abundance plot

hgroups_ants <- cutree(sclust, k = 50)
nonSpikes20A <- nonSpikes20 %>% left_join(
  tibble(ASV = names(hgroups_ants), cluster = hgroups_ants), by = "ASV")
# ASVsToView <- nonSpikes20A %>%
#   filter(Kingdom == "Bacteria") %>%
#   group_by(ASV, cluster) %>%
#   summarise(meanCopies = mean(copiesPerL)) %>%
#   group_by(cluster) %>%
#   summarize(topASV = ASV[which.max(meanCopies)])
  
ClusterSumsA <- nonSpikes20A %>%
  group_by(Station, Depth, cluster, Size_Class, Bin_Size) %>%
  summarise(copiesPerL = sum(copiesPerL))
`summarise()` has grouped output by 'Station', 'Depth', 'cluster', 'Size_Class'. You can override using the `.groups` argument.
HugeSurfacePlot <- nonSpikes20A %>%
  filter(Depth == "Surface") %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster ~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 4)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth == "Surface")) # Add sums
ggsave("HugeSurfacePlot.pdf", HugeSurfacePlot, height = 72, width = 8, limitsize = FALSE)
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

I think we’re using “intercept” in the clustering information somehow. Which I don’t particularly want. But the clustering does happen by correlation. Super strange. Maybe the correlation isn’t the way I think it is?

MinimalSurfacePlot <- nonSpikes20A %>%
  filter(Depth == "Surface", cluster %in% c(1, 7, 15)) %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth == "Surface", cluster %in% c(1, 7, 15))) # Add sums
ggsave("MinimalSurfacePlot.pdf", MinimalSurfacePlot, height = 11, width = 8, limitsize = FALSE)
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis
MinimalSurfacePlot
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

MinimalClusterPlot <- nonSpikes20A %>%
  filter(Depth != "Oxy", cluster %in% c(1, 7, 15)) %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster + Depth ~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth != "Oxy", cluster %in% c(1, 7, 15))) # Add sums
ggsave("MinimalClusterPlot.pdf", MinimalClusterPlot, height = 11, width = 8, limitsize = FALSE)
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

For sairah specifically

ExampleTaxa <- nonSpikes20 %>%
  filter(ASV %in% c("ASV_3", "ASV_23", "ASV_459")) %>%
  filter(Station %in% c("3.3", "4.3")) %>%
  mutate(Depth = recode(Depth, Oxy = "Oxycline")) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Depth), shape = as.factor(Depth))) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Station ~ Tag) +
  geom_point(size = 4) +
  geom_path(aes(color = as.factor(Depth))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "right") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station")
ExampleTaxa
Warning: Transformation introduced infinite values in continuous y-axis
Warning: Transformation introduced infinite values in continuous y-axis

Thing 2

abunPlot0 <- microbialAbundance %>% 
  filter(is.finite(MassperLiter)) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  mutate(Depth = recode(Depth, Oxy = "Oxycline")) %>%
  mutate(copiesPerMg = copiesPerL / MassperLiter) %>%
  ggplot(aes(x = Size_Class, y = copiesPerMg, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice() +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "16s + 18s Genes / mg Particles", x = expression(paste("Particle Size (", mu, "m)")), color = "Depth", fill = "Depth", shape = "Depth") +
  theme(plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
SairahLegend <- get_legend(abunPlot0)
abunPlot <- abunPlot0 + theme(legend.position = "none")
#abunPlot
PPLPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  ggplot(aes(x = Size_Class, y = ParticlesPerLiter, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag=seq(-10,20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "Particles/L/mm", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
#PPLPlot
ParticleMassPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  ggplot(aes(x = Size_Class, y = MassperLiter/ParticlesPerLiter, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "Dry Mass (mg) / Particle", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = .5))
#ParticleMassPlot
x.grob <- textGrob(expression(paste("Particle Size (", mu, "m)")), 
                   gp=gpar(fontsize=16))
combinedPlot <- plot_grid(PPLPlot, ParticleMassPlot, abunPlot, nrow = 1, labels = c("A", "B", "C"))
meta2 <- grid.arrange(arrangeGrob(combinedPlot, bottom = x.grob), right = SairahLegend)

---
title: "R Notebook"
output: html_notebook
---

# Initial Stuff

Load in Initial Processing file (and dependencies)

```{r}
source("InitialProcessing.R")
source("ChesapeakePersonalLibrary.R")
```


# Cells/mg of particle

```{r}
# my_sizes <- sort(unique(microbialAbundance$Size_Class))
# my_sizes
```

```{r}
# scientific_10_c <- function(x) {
#     xout <- gsub("1e", "10^{", format(x),fixed=TRUE)
#     xout <- gsub("{-0", "{-", xout,fixed=TRUE)
#     xout <- gsub("{+", "{", xout,fixed=TRUE)
#     xout <- gsub("{0", "{", xout,fixed=TRUE)
#     xout <- paste(xout,"}",sep="")
#     return(parse(text=xout))
#     
# }
# 
# scale_y_log10nice <- function(name=NULL,omag=seq(-10,20),...) {
#     breaks10 <- 10^omag
#     scale_y_log10(breaks=breaks10,labels=scientific_10_c(breaks10),...)
# } # Reclocated to ChesapeakePersonalLibrary.R
```


```{r}
abunPlot <- microbialAbundance %>% 
  filter(is.finite(MassperLiter)) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  mutate(copiesPerMg = copiesPerL / MassperLiter) %>%
  ggplot(aes(x = Size_Class, y = copiesPerMg, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice() +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "16s + 18s Genes / mg Particles", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
abunPlot
```

```{r}
PPLPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  ggplot(aes(x = Size_Class, y = ParticlesPerLiter, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag=seq(-10,20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "Particles/L/mm", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
PPLPlot
```

```{r}
ParticleMassPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  filter(Depth %in% c("Surface", "Bottom")) %>%
  ggplot(aes(x = Size_Class, y = MassperLiter/ParticlesPerLiter, shape = as.factor(Station), fill = as.factor(Station))) +
  facet_wrap(~Depth, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Station))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  labs(y = "Dry Mass (mg) / Particle", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = .5))
ParticleMassPlot
```

# Ibid but combined with data about particles and the CB map
I need to load over data from the CB-Bay project

```{r}
source("CBMap.R")
```

```{r}
library(cowplot)
library(grid)
library(gridExtra)
```

```{r}
x.grob <- textGrob(expression(paste("Particle Size (", mu, "m)")), 
                   gp=gpar(fontsize=16))
```


```{r fig.height = 4, fig.width = 11}
combinedPlot <- plot_grid(PPLPlot, ParticleMassPlot, abunPlot, nrow = 1, labels = c("B", "C", "D"))
```

```{r}
meta2 <- grid.arrange(arrangeGrob(combinedPlot, bottom = x.grob))
```

```{r}
cbMap
```


```{r}
physical_particles <- plot_grid(cbMap, meta2, rel_widths = c(1,3), labels = c("A", ""))
physical_particles
```

```{r}
ggsave("PhysicalParticles.png", physical_particles, height = 4, width = 8)
```



# Examplar species plot

What are the most abundant ASVs from each cluster?
Plot their abundance.
Pick the prettiest few and plot

```{r}
source("ClusteringCore.R")
```


```{r}
hgroups_exemplars <- cutree(sclust, k = 10)
```


```{r}
nonSpikes20C <- nonSpikes20 %>% left_join(
  tibble(ASV = names(hgroups_exemplars), cluster = hgroups_exemplars), by = "ASV")
ASVsToView <- nonSpikes20C %>%
  filter(Kingdom == "Bacteria") %>%
  group_by(ASV, cluster) %>%
  summarise(meanCopies = mean(copiesPerL)) %>%
  group_by(cluster) %>%
  summarize(topASV = ASV[which.max(meanCopies)])
  
```

```{r}
ASVsToView
```



```{r}
nonSpikes20C %>% 
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster")) %>%
  group_by(ASV) %>%
  slice_head()
```





```{r fig.width = 10}
nonSpikes20C %>%
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster" = "cluster")) %>%
  filter(cluster <= 7, Depth %in% c("Surface", "Bottom"), !is.na(Depth)) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma")
```
Fig X. Copies per L

```{r fig.width = 10}
nonSpikes20C %>%
  right_join(ASVsToView, by = c("ASV" = "topASV", "cluster" = "cluster")) %>%
  filter(cluster <= 7, Depth %in% c("Surface", "Bottom"), !is.na(Depth)) %>%
  filter(!is.na(MassperLiter)) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/MassperLiter, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma")
```
Fig X + 1. Copies per mg stuff.
I don't love these examples because there is a bunch of station to station ariance, and you never see things that like, always show up at large stations.

I wonder if I can find some good examples of consistantly large particle stuff or something.

# What if
I look for things that have high positive slope coefficients between size and normalized copies per L.
And select for high mean abundance and high slope.
And use site as a random effect?
Would be nice to have some things that are intermediately high though.
Some sort of polynomial regression?

```{r}
nest20 <- nonSpikes20 %>%
  select(ASV, Station:ParticlesPerLiter, copiesPerL) %>%
  mutate(Station = as.factor(Station)) %>%
  group_by(ASV) %>%
  nest()
```

```{r}
TestSub <- nest20[[2]][[1]] %>% ungroup()
TestSub
```

```{r}
library(lme4)
library(broom)
library(broom.mixed)
```

```{r}
lm(log(copiesPerL/Bin_Size) ~ log(Size_Class), data = TestSub) %>% tidy()
```

```{r}
lmer(log(copiesPerL/Bin_Size) ~ log(Size_Class) + (Size_Class|Station) + (Size_Class|Depth) , data = TestSub %>% 
       mutate(as.factor(Station))) %>% AIC()

lmer(log(copiesPerL/Bin_Size) ~ log(Size_Class) + (1|Station) + (1|Depth) , data = TestSub %>% 
       mutate(as.factor(Station))) %>% AIC() # Better
```

```{r}
modDf <- nest20 %>%
  mutate(mod = map(data, 
                   ~lmer(log((copiesPerL+1)/Bin_Size) ~ log(Size_Class) +
                           (Size_Class|Station) + (Size_Class|Depth), data = .)
  )
  )
```

```{r}
modDf01 <- modDf %>% 
  mutate(tidied = map(mod, tidy)) %>%
  unnest(tidied) %>%
  select(-data, -mod)
```

```{r}
modDf02 <- modDf01 %>%
  filter(term == "log(Size_Class)") %>%
  select(ASV, estimate, std.error)
```

```{r}
modDf02 %>%
  ggplot(aes(x = estimate)) + geom_histogram() +
  scale_x_continuous(breaks = seq(from = -4, to = 2, by = 1))
```
There are some things that are ore abundant in the large particles

So Many ASVs. How do I ID the ones I want?

I kind of want to look at average concentrations (or sums)

```{r}
SlopesAndMeans <- nonSpikes20 %>%
  #filter(Kingdom == "Bacteria") %>%
  group_by(ASV) %>%
  summarise(meanCopies = mean(copiesPerL)) %>%
  left_join(modDf02, by = "ASV")
SlopesAndMeans %>% head()
```

```{r}
SlopesAndMeans %>%
  filter(estimate >= 0) %>%
  ggplot(aes(x = estimate, y = meanCopies, label = ASV)) +
  geom_point() +
  geom_label_repel()
```
ASV 13 looks promising

```{r}
taxa %>% 
  filter(ASV %in% c("ASV_13", "ASV_23", "ASV_58"))
```

The big stuff are all cyanos! Huh.

```{r}
Targets <- SlopesAndMeans %>% filter(estimate > 0, meanCopies > 1e5) %>% pull(ASV)
taxa %>%
  filter(ASV %in% Targets)
```

```{r}
Horses <- SlopesAndMeans %>% 
  left_join(taxa, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 0e5) %>%
  arrange(-meanCopies)
Horses
```

Ok. Big stuff are cyanos and Planctomycetes, and apparently Spiders.
Also apparently some proteos of different stripes. Rhodobacter are cool though.

```{r fig.width = 10}
nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
```

```{r fig.width = 10}
nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies > 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  filter(ASV == "ASV_7") %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
```

```{r fig.width = 10}
nonSpikes20 %>%
  left_join(SlopesAndMeans, by = "ASV") %>%
  filter(estimate > 0, meanCopies < 1e5, Depth != "Oxy") %>%
  arrange(-meanCopies, Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice() + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 2) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 90))
```

Lets look at these!

I like, as examples Paracoccus (a Rhodobacter) -ASV_459
Synechococcus_CC9902 -- ASV_23
SAR11_Clade -- ASV_3

```{r}
nonSpikes20 %>%
  filter(ASV %in% c("ASV_3", "ASV_23", "ASV_459"), Depth != "Oxy") %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Station), shape = as.factor(Station))) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Depth ~ Tag) +
  geom_point(size = 3) +
  geom_path(aes(color = as.factor(Station))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_viridis_d(option = "plasma") +
  scale_color_viridis_d(option = "plasma") +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station")
```



# Module abundance plot

```{r}
hgroups_ants <- cutree(sclust, k = 50)
```


```{r}
nonSpikes20A <- nonSpikes20 %>% left_join(
  tibble(ASV = names(hgroups_ants), cluster = hgroups_ants), by = "ASV")
# ASVsToView <- nonSpikes20A %>%
#   filter(Kingdom == "Bacteria") %>%
#   group_by(ASV, cluster) %>%
#   summarise(meanCopies = mean(copiesPerL)) %>%
#   group_by(cluster) %>%
#   summarize(topASV = ASV[which.max(meanCopies)])
  
```

```{r}
ClusterSumsA <- nonSpikes20A %>%
  group_by(Station, Depth, cluster, Size_Class, Bin_Size) %>%
  summarise(copiesPerL = sum(copiesPerL))
```


```{r}
HugeSurfacePlot <- nonSpikes20A %>%
  filter(Depth == "Surface") %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster ~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 4)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth == "Surface")) # Add sums
ggsave("HugeSurfacePlot.pdf", HugeSurfacePlot, height = 72, width = 8, limitsize = FALSE)
```

I think we're using "intercept" in the clustering information somehow. Which I don't particularly want. But the clustering does happen by correlation. Super strange. Maybe the correlation isn't the way I think it is?

```{r}
MinimalSurfacePlot <- nonSpikes20A %>%
  filter(Depth == "Surface", cluster %in% c(1, 7, 15)) %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth == "Surface", cluster %in% c(1, 7, 15))) # Add sums
ggsave("MinimalSurfacePlot.pdf", MinimalSurfacePlot, height = 11, width = 8, limitsize = FALSE)
```

```{r}
MinimalSurfacePlot
```


```{r}
MinimalClusterPlot <- nonSpikes20A %>%
  filter(Depth != "Oxy", cluster %in% c(1, 7, 15)) %>%
  arrange(Bin_Size) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class)) +
  facet_grid(cluster + Depth ~ Station) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  geom_path(alpha = 0.5, aes(group = ASV)) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "none") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station") +
  geom_path(color = "red", data = ClusterSumsA %>% filter(Depth != "Oxy", cluster %in% c(1, 7, 15))) # Add sums
ggsave("MinimalClusterPlot.pdf", MinimalClusterPlot, height = 11, width = 8, limitsize = FALSE)
```


# For sairah specifically

```{r}
ExampleTaxa <- nonSpikes20 %>%
  filter(ASV %in% c("ASV_3", "ASV_23", "ASV_459")) %>%
  filter(Station %in% c("3.3", "4.3")) %>%
  mutate(Depth = recode(Depth, Oxy = "Oxycline")) %>%
  arrange(Size_Class) %>%
  ggplot(aes(y = copiesPerL/Bin_Size, x = Size_Class, fill = as.factor(Depth), shape = as.factor(Depth))) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) + scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  facet_grid(Station ~ Tag) +
  geom_point(size = 4) +
  geom_path(aes(color = as.factor(Depth))) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  theme_bw(base_size = 14) +
  theme(axis.text.x = element_text(angle = 90), legend.position = "right") +
  labs(y = "16s Copies/L/mm", x = expression(paste("Particle Size (", mu, "m)")), fill = "Station", color = "Station", shape = "Station")
ExampleTaxa
```

### Thing 2


```{r}
abunPlot0 <- microbialAbundance %>% 
  filter(is.finite(MassperLiter)) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  mutate(Depth = recode(Depth, Oxy = "Oxycline")) %>%
  mutate(copiesPerMg = copiesPerL / MassperLiter) %>%
  ggplot(aes(x = Size_Class, y = copiesPerMg, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice() +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "16s + 18s Genes / mg Particles", x = expression(paste("Particle Size (", mu, "m)")), color = "Depth", fill = "Depth", shape = "Depth") +
  theme(plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
SairahLegend <- get_legend(abunPlot0)
abunPlot <- abunPlot0 + theme(legend.position = "none")
#abunPlot
```

```{r}
PPLPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  ggplot(aes(x = Size_Class, y = ParticlesPerLiter, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag=seq(-10,20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "Particles/L/mm", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = 0))
#PPLPlot


```

```{r}
ParticleMassPlot <- microbialAbundance %>%
  filter(Size_Class >= 1) %>%
  #filter(Depth %in% c("Surface", "Bottom")) %>%
  filter(Station %in% c(3.3, 4.3)) %>%
  ggplot(aes(x = Size_Class, y = MassperLiter/ParticlesPerLiter, shape = as.factor(Depth), fill = as.factor(Depth))) +
  facet_wrap(~Station, ncol = 1) +
  theme_bw(base_size = 16) +
  geom_point(size = 4) +
  #geom_path() + 
  geom_path(aes(color = as.factor(Depth))) +
  scale_x_log10(breaks = my_sizes, labels = as.character(my_sizes)) +
  scale_y_log10nice(omag = seq(-10, 20, by = 2)) +
  scale_shape_manual(values = rep(21:25, 2)) +
  scale_fill_manual(values = c("green", "blue", "black")) +
  scale_color_manual(values = c("green", "blue", "black")) +
  labs(y = "Dry Mass (mg) / Particle", x = expression(paste("Particle Size (", mu, "m)"))) +
  theme(legend.position = "none",
        plot.margin = unit(c(0, 0, 0, 0), "cm"),
        axis.title.x = element_blank(),
        axis.text.x = element_text(angle = 90, vjust = .5),
        axis.title.y = element_text(margin = unit(c(0, 0, 0, 0), "mm"), vjust = .5))
#ParticleMassPlot
```

```{r}
x.grob <- textGrob(expression(paste("Particle Size (", mu, "m)")), 
                   gp=gpar(fontsize=16))
```


```{r fig.height = 4, fig.width = 11}
combinedPlot <- plot_grid(PPLPlot, ParticleMassPlot, abunPlot, nrow = 1, labels = c("A", "B", "C"))
```

```{r}
meta2 <- grid.arrange(arrangeGrob(combinedPlot, bottom = x.grob), right = SairahLegend)
```